Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1/README.md

language, license, tags, base_model, pipeline_tag

language	license	tags	base_model	pipeline_tag
en de	apache-2.0	chat GGUF mlx	Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1	text-generation

mlx-community/Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1

The Model mlx-community/Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1 was converted to MLX format from Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1 using mlx-lm version 0.21.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)